DeepScaleR

DeepScaleR

Agentica Project
Mathstral

Mathstral

Mistral AI
+
+

Related Products

  • LeaseAccounting.app
    Visit Website
  • BYDFi
    5,934 Ratings
    Visit Website
  • Runpod
    220 Ratings
    Visit Website
  • PackageX OCR Scanning
    48 Ratings
    Visit Website
  • Setplex
    10 Ratings
    Visit Website
  • Criminal IP ASM
    19 Ratings
    Visit Website
  • LTX
    182 Ratings
    Visit Website
  • Evertune
    1 Rating
    Visit Website
  • Eurekos
    83 Ratings
    Visit Website
  • Dynamo Software
    71 Ratings
    Visit Website

About

DeepScaleR is a 1.5-billion-parameter language model fine-tuned from DeepSeek-R1-Distilled-Qwen-1.5B using distributed reinforcement learning and a novel iterative context-lengthening strategy that gradually increases its context window from 8K to 24K tokens during training. It was trained on ~40,000 carefully curated mathematical problems drawn from competition-level datasets like AIME (1984–2023), AMC (pre-2023), Omni-MATH, and STILL. DeepScaleR achieves 43.1% accuracy on AIME 2024, a roughly 14.3 percentage point boost over the base model, and surpasses the performance of the proprietary O1-Preview model despite its much smaller size. It also posts strong results on a suite of math benchmarks (e.g., MATH-500, AMC 2023, Minerva Math, OlympiadBench), demonstrating that small, efficient models tuned with RL can match or exceed larger baselines on reasoning tasks.

About

As a tribute to Archimedes, whose 2311th anniversary we’re celebrating this year, we are proud to release our first Mathstral model, a specific 7B model designed for math reasoning and scientific discovery. The model has a 32k context window published under the Apache 2.0 license. We’re contributing Mathstral to the science community to bolster efforts in advanced mathematical problems requiring complex, multi-step logical reasoning. The Mathstral release is part of our broader effort to support academic projects, it was produced in the context of our collaboration with Project Numina. Akin to Isaac Newton in his time, Mathstral stands on the shoulders of Mistral 7B and specializes in STEM subjects. It achieves state-of-the-art reasoning capacities in its size category across various industry-standard benchmarks. In particular, it achieves 56.6% on MATH and 63.47% on MMLU, with the following MMLU performance difference by subject between Mathstral 7B and Mistral 7B.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Researchers, students, and developers interested in an AI model capable of mathematical reasoning and logic tasks without requiring heavy hardware

Audience

Individuals focused on mathematical research looking for an AI tool to enhance their problem-solving capabilities

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version
Free Trial

Pricing

Free
Open source
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Agentica Project
Founded: 2025
United States
agentica-project.com

Company Information

Mistral AI
Founded: 2023
France
mistral.ai/news/mathstral/

Alternatives

DeepCoder

DeepCoder

Agentica Project

Alternatives

Mistral Large 2

Mistral Large 2

Mistral AI
Mistral NeMo

Mistral NeMo

Mistral AI
Phi-4-reasoning

Phi-4-reasoning

Microsoft
Solar Pro 2

Solar Pro 2

Upstage AI
Claude Opus 3

Claude Opus 3

Anthropic
Athene-V2

Athene-V2

Nexusflow
Mistral Large

Mistral Large

Mistral AI

Categories

Categories

Integrations

Airtrain
AlphaCorp
Arize Phoenix
Codestral
Codestral Mamba
Continue
DataChain
Diaflow
GaiaNet
Hugging Face
LM-Kit.NET
Lunary
Ministral 8B
Motific.ai
Overseer AI
PI Prompts
Superinterface
SydeLabs
Wordware
Yaseen AI

Integrations

Airtrain
AlphaCorp
Arize Phoenix
Codestral
Codestral Mamba
Continue
DataChain
Diaflow
GaiaNet
Hugging Face
LM-Kit.NET
Lunary
Ministral 8B
Motific.ai
Overseer AI
PI Prompts
Superinterface
SydeLabs
Wordware
Yaseen AI
Claim DeepScaleR and update features and information
Claim DeepScaleR and update features and information
Claim Mathstral and update features and information
Claim Mathstral and update features and information